Note: Descriptions are shown in the official language in which they were submitted.
DETAILED DESCRIPTION OF THE INVENTION
[1] This section is intended to provide explanation and description of
various possible
embodiments of the present invention. The embodiments used herein, and various
features and
advantageous details thereof are explained more fully with reference to non-
limiting
embodiments illustrated in the accompanying drawings and detailed in the
following
description. The examples used herein are intended only to facilitate an
understanding of ways
in which the embodiments herein may be practiced and to further enable the
person skilled in
the art to practice the embodiments used herein. Also, the
examples/embodiments described
herein should not be construed as limiting the scope of the embodiments
herein. Corresponding
reference numerals indicate corresponding parts throughout the drawings.
[2] The present invention discloses automated generation or creation of a
draft response to
an email communication received by a user on an electronic device. A rule
engine is provided
to generate one or more rules based on at least one input from the user. An AT
module (artificial
intelligence-based module) is configured to identify one or more keywords from
the email
communication received by the user, to analyze context of the email.
Subsequently, the draft
response is generated and displayed to the user, based on the analysed context
of the email and
the one or more rules.
[3] As used herein, 'processing unit' is an intelligent device or module,
that is capable of
processing digital logics and also possesses analytical skills for analyzing
and processing
various rental management related data or information, according to the
embodiments of the
present invention.
[4] As used herein, 'database' refers to a local or remote memory device;
docket systems;
storage units; each capable to store information including, data pertaining to
email processing,
user data, user email account data, user profiles, location data, predefined
rules, categories and
types of emails, emails received by a user, draft responses to be sent as
email replies by the
user, and other data and related information. In an embodiment, the storage
unit may be a
database server, a cloud storage, a remote database, a local database.
[5] As used herein, 'user device' or 'electronic device' is a smart
electronic device capable
of communicating with various other electronic devices and applications via
one or more
communication networks. Examples of said user device include, but not limited
to, a wireless
Date Recue/Date Received 2022-02-09
communication device, a smart phone, a tablet, a desktop, a laptop, etcetera.
The user device
comprises: an input unit to receive one or more input data; an operating
system to enable the
user device to operate; a processing unit to process various data and
information; a memory
unit to store initial data, intermediary data and final data pertaining to
claims data; and an
output unit having a graphical user interface (GUI).
[6] As used herein, 'module' or 'unit' refers to a device, a system, a
hardware, a computer
application configured to execute specific functions or instructions according
to the
embodiments of the present invention. The module or unit may include a single
device or
multiple devices configured to perform specific functions according to the
present invention
disclosed herein.
[7] As used herein, 'communication network' includes a local area network
(LAN), a wide
area network (WAN), a metropolitan area network (MAN), a virtual private
network (VPN), an
enterprise private network (EPN), Internet, and a global area network (GAN).
[8] Terms such as 'connect', 'integrate', 'configure', and other similar
terms include a
physical connection, a wireless connection, a logical connection or a
combination of such
connections including electrical, optical, RF, infrared, Bluetooth, or other
transmission media,
and include configuration of software applications to execute computer program
instructions, as
specific to the presently disclosed embodiments, or as may be obvious to a
person skilled in the
art.
[9] Terms such as 'send', 'transfer', 'transmit', 'receive', 'collect',
'obtain', 'access' and
other similar terms refers to transmission of data between various modules and
units via wired
or wireless connections across a communication network.
[10] Figure 1 illustrates architecture of a system 100 for automatically
generating a draft
response to an email communication received by a user on an electronic device,
according to an
exemplary embodiment of the present invention. The system 100 comprises a
frontend module
102, a backend module 104, at least one electronic device 106 (user device
106), an API
(Application Programming Interface) module, a rule engine, an Al (artificial
intelligence)
module, a database 112 and a template generating module.
[11] The system also comprises a server that is communicatively connected to
the database
112 and various other modules in a communication network for providing remote
management
of data. The frontend module 102 is connected in the network and configured to
interact with
Date Recue/Date Received 2022-02-09
the user for receiving at least one user input. The frontend module 102 is
configured for the
user to interact and add email accounts to be automated. The rule engine is a
processing unit
that is configured to generate one or more rules based on the at least one
user input. The user
inputs are the data entered by the users as per their requirements. The user
enters or feeds the
data/user input by using corresponding user device 106 or electronic device
106. The AT
module 118 is an artificial intelligence-based module with machine learning
capabilities. The
AT module 118 is configured to identify one or more keywords from the email
communication
received by the user, in order to analyze context of the email. Thereafter,
based on the analysed
context of the email and the generated one or more rules, the AT module 118
generates the draft
response based for the user.
[12] According to the embodiments of the present subject matter, the one or
more rules
include, but is not limited to 'to ignore emails based on the sender'; to
ignore emails based on
the content'; 'forwarding emails using any specific content'; etc.
Additionally, templates being
selected can also be included as user rules. Further, in an event if a sender
of an email sends an
inquiry, then rules may be set to respond with a given text by the user.
[13] According to an embodiment of the present disclosure, the AT module 118
reads content
of the received email to identify the one or more keywords. Further, each rule
of the one or
more rules is applied to a corresponding template, wherein the corresponding
template is being
personalized based on the content of the received email. The AT module 118
categorizes the
received email into one or more types to thereby generate the draft response
for each type of
category. The API (Application Programming Interface) module that sends
relevant information
to the AT module 118, the relevant information pertaining to the added email
accounts.
[14] According to an embodiment of the present disclosure, the AT module 118
executes
specific enhanced algorithm to provide customized responses to users who
receive emails and
wish to respond to the received emails automatically. The AT module 118 is
associated with
machine learning capabilities that facilitate in constantly learning new
information to
incorporate into the email communication for thereby generating personalized
email content for
each of the received emails which are to be delivered to each of the
recipients. The AT module
118 analyses the received email and in order to prepare a reply, it analyses
the context of the
email. The reply as prepared or generated by the AT module 118 is customized
according to the
user requirements. For example, if an email is received by a user and a simple
Date Recue/Date Received 2022-02-09
acknowledgement has to be sent to the sender, then the AT module 118 will
generate an
acknowledgement email wherein a template for the acknowledgement message will
be used by
the AT module 118. On the other hand, if the AT module 118 analyses that any
specific
information has to be added to the email content, it will search for the
content from the database
112 and add the same in the email body to accordingly prepare a suitable
response. The Al
module 118 also takes as input a user's rules, which are set by the rule
engine 116 and displayed
to the users on their dashboard. The rules are used to reply to emails by
reading the content and
sending across the reply based on the keywords in the email. Initially, the AT
module 118
iterates through all rules as set or inputted by the user via the electronic
device 106. Each rule is
applied to specific templates which are then personalized as per the content
of the opposite
party's email.
[15] This way, the AT module 118 is configured to analyse all requirements of
the user, to
understand context of the email message/communication, and accordingly
generate a suitable
reply to the email communication. The users do not have to prepare the
response manually and
are able to save a lot of time. As per the embodiments of the subject matter
as disclosed herein,
web-based applications or mobile-based applications may be provided to
implement the AT
module 118 to generate response drafts. This is different to the conventional
methods of
predicting the response sentences, words, and giving options. The emails
written by AT module
118 are a lot more elaborate and personalized for respective users. Further,
the drafted email
responses are longer, elaborate, and can also schedule meetings based on the
draft.
Furthermore, the response generated is a lot more personalized due to the
artificial intelligence
learning information about the recipient based on previous or historical
correspondences.
[16] In various embodiments of the present invention, the AT module 118 is
configured to
categorize the type of email received and picks an appropriate response using
the pre-assigned
templates/ information. This acts as an email plugin, where after initially
connecting it to email
applications on the respective electronic devices 106, a user need not require
to make any
further connection or configuration. The user may send the email draft as soon
as it is generated
or go to the site to adjust the rules or edit as per specific requirements.
[17] The frontend module 102 may be configured as a web application which
connects to a
system with an SQL database 112 for storing and querying user records and
information along
with user authentication. The AT module 118 connects to the database 112 to
access the saved
Date Recue/Date Received 2022-02-09
emails. The required information is passed to the machine learning model. The
machine
learning model is pre-trained using custom data, which tokenize strings (split
words into
vectors) and build a method of classification to ensure when emails are read,
they are
categorized correctly.
[18] The frontend module 102 is configured for the user to interact and add
email accounts to
be automated. The frontend module 102 is connected to backend module 104 and
database 112
which stores user information and has API paths 114 for signing the users sign
in. In addition,
the API module 108 that will connect to email accounts and pass information to
the machine
learning model which will categorize the email received and respond
appropriately using the
information provided. The machine learning model is trained using one or more
mechanisms.
Using the learning model of the AT module 118, custom data and labels are
passed in so the
model can be fine-tuned to categorize emails based on the wanted labels or
types. Along with
this, the general neural network is customized to ensure the model is trained
appropriately to
the data wanted, by customizing the amount of data passed in, number of
iteration and such
details. The user is also facilitated to automate several other tasks
associated with email
management. This helps in reducing time spent in reading and writing emails.
The AT module
118 with machine learning capabilities and pre-assigned templates, as
generated by the template
generating module 110, are used to generate draft responses of emails and are
also used in other
tasks, such as scheduling meetings in a way that reduces the amount of back
and forth.
[19] Figure 2 illustrates working of a transformer encoder 200 for
automatically generating a
draft response to an email communication received by a user on an electronic
device 106,
according to an exemplary embodiment of the present invention disclosure. The
figure
describes working of the transformer to transform the words to numbers. Once
the email is
received, the content of the email is analysed to identify words and keywords.
Words are then
passed in and they are converted to the numbers using the information inside
the transformer.
Thereafter, using the knowledge inside of the transformer, weights ("w" and
"V") are assigned
for which words connect which others. The reason words are converted into
numbers is because
that way words can be matched with the words previously learned in the model
or match it with
similar words. Additionally, this makes it possible for the AT module to learn
the context of
words by seeing what comes before and after. Further, the weight of words on
the outcome is
also checked by the process of tokenization. For example, a sentence "Hi, I am
Jas" would go
Date Recue/Date Received 2022-02-09
into the model and be treated as numbers such as [1,0,0,0],
[0,1,0,0].[0,0,1,0], [0Ø0,1].
Assuming, the model only knows 4 words, (the more words, the more zeros are
necessary), this
way the model can easily know what is being referred and can apply the
necessary math on
these value in predictions. Outputting the information that the machine
learning model being
trained can use to figure out the importance of words in a sentence and how to
classify them.
The transformer is a pre-trained model, that may be trained on a large dataset
to provide a wider
understanding. The transformer may b provided with custom data and can be
trained to predict
according to custom data, by changing the weights of what it learns and
improving itself to fit
the use case.
[20] Figure 3 illustrates the method for automatically generating a draft
response to an email
communication received by a user on an electronic device 106. The structural
elements
performing these method steps have been described in detail in description of
Fig. 1 and Fig.2.
Given below are the steps of the method according to the embodiments of the
present subject
matter.
[21] At step 302, at least one user input is received from a user via
corresponding user device
106 or electronic device 106. An AT module 118, via the server, may be
communicatively
connected to the database 112 in the communication network; A frontend module
102 or device
may be connected in the communication network to interact with the user for
receiving at least
one user input via the electronic device 106.
[22] At step 304, a rule engine 116 configured to generate one or more rules
based on the at
least one user input. The user rules sets are pulled in the backend. The rule
engine 116 is in
communication with the backend module 104, so when the user sets up the rules,
it gets saved
there and can be pulled in, along with automating calls.
[23]
[24] At step 306, the AT module 118 (artificial intelligence-based module) is
configured to
identify one or more keywords from the email communication received by the
user, to analyze
context of the email.
[25] At step 308, the draft response is generated based on the analysed
context of the email
and the generated one or more rules.
[26] According to an embodiment of the present disclosure, the AT module 118
reads content
of the received email to identify the one or more keywords.
Date Recue/Date Received 2022-02-09
[27] According to an embodiment of the present disclosure, each rule of the
one or more
rules is applied to a corresponding template, the corresponding template being
personalized
based on the content of the received email. The frontend module 102 is
configured for the user
to interact and add email accounts to be automated. Further, the API
(Application Programming
Interface) module is configured that sends relevant information to the Al
module 118, the
relevant information pertaining to the added email accounts. The Al module 118
categorizes the
received email into one or more types to thereby generate the draft response
for each type of
category.
[28] It will be understood by those skilled in the art that the figures are
only a representation
of the structural components and process steps that are deployed to provide an
environment for
the solution of the present invention disclosure discussed above, and does not
constitute any
limitation. The specific components and method steps may include various other
combinations
and arrangements than those shown in the figures.
[29] The term exemplary is used herein to mean serving as an example. Any
embodiment or
implementation described as exemplary is not necessarily to be construed as
preferred or
advantageous over other embodiments or implementations. Further, the use of
terms such as
including, comprising, having, containing and variations thereof, is meant to
encompass the
items/components/process listed thereafter and equivalents thereof as well as
additional
items/components/process.
[30] Although the subject matter is described in language specific to
structural features
and/or acts, it is to be understood that the subject matter defined in the
claims is not necessarily
limited to the specific features or process as described above. In fact, the
specific features and
acts described above are disclosed as mere examples of implementing the claims
and other
equivalent features and processes which are intended to be within the scope of
the claims.
Date Recue/Date Received 2022-02-09
111
Date Recue/Date Received 2022-02-09
SUMMARY
[1] In order to provide a holistic solution to the above-mentioned
limitations, it is necessary
to deploy a solution for automatically generating email responses for users.
[2] An object of the present disclosure is to prepare drafts of customized
responses to
emails received by the users.
[3] Another object of the present disclosure is to provide artificial
intelligence capability to
facilitate constant learning of new information to incorporate into the
communication to further
send personalized emails to each recipient.
[4] According to an embodiment of the present disclosure, there is provided
a
computer-implemented system for automatically generating a draft response to
an email
communication received by a user on an electronic device, the system
comprising: a server
communicatively connected to a database in a communication network; a frontend
module
connected in the network and configured to interact with the user for
receiving at least one user
input; a rule engine configured to generate one or more rules based on the at
least one user
input; an AT module (artificial intelligence-based module) configured to:
identify one or more
keywords from the email communication received by the user, to analyze context
of the email;
generate the draft response based on the analysed context of the email and the
generated one or
more rules.
[5] According to an embodiment of the present disclosure, the AT module
reads content of
the received email to identify the one or more keywords.
[6] According to an embodiment of the present disclosure, each rule of the
one or more
rules is applied to a corresponding template, the corresponding template being
personalized
based on the content of the received email.
[7] According to an embodiment of the present disclosure, the frontend
module is
configured for the user to interact and add email accounts to be automated.
[8] According to an embodiment of the present disclosure, an API
(Application
Programming Interface) module that sends relevant information to the AT
module, the relevant
information pertaining to the added email accounts.
Date Recue/Date Received 2022-02-09
[9]
According to an embodiment of the present disclosure, the AT module
categorizes the
received email into one or more types to thereby generate the draft response
for each type of
category.
[10] According to an embodiment of the present disclosure, a computer-
implemented
method is provided for automatically generating a draft response to an email
communication
received by a user on an electronic device. The method comprises: configuring
a server
communicatively connected to a database in a communication network;
configuring a frontend
module connected in the communication network to interact with the user for
receiving at least
one user input; a rule engine configured to generate one or more rules based
on the at least one
user input; configuring an AT module (artificial intelligence-based module)
to: identify one or
more keywords from the email communication received by the user, to analyze
context of the
email; generate the draft response based on the analysed context of the email
and the generated
one or more rules.
[11] The afore-mentioned objectives and additional aspects of the embodiments
herein will
be better understood when read in conjunction with the following description
and
accompanying drawings. It should be understood, however, that the following
descriptions,
while indicating preferred embodiments and numerous specific details thereof,
are given by
way of illustration and not of limitation. This section is intended only to
introduce certain
objects and aspects of the present invention, and is therefore, not intended
to define key
features or scope of the subject matter of the present invention.
111
Date Recue/Date Received 2022-02-09
BRIEF DESCRIPTION OF THE DRAWINGS
[1] The figures mentioned in this section are intended to disclose
exemplary embodiments
of the claimed system and method. Further, the components/modules and steps of
a process are
assigned reference numerals that are used throughout the description to
indicate the respective
components and steps. Other objects, features, and advantages of the present
invention will be
apparent from the following description when read with reference to the
accompanying
drawings:
[2] Figure 1 illustrates a system architecture, according to an exemplary
embodiment of the
invention disclosure;
[3] Figure 2 illustrates working of a transformer encoder implemented for
automatically
generating a draft response to an email communication received by a user on an
electronic
device, according to an exemplary embodiment of the present invention
disclosure; and
[4] Figure 3 illustrates the method for automatically generating a draft
response to an email
communication received by a user on an electronic device, according to an
exemplary
embodiment of the present invention disclosure.
[5] Like reference numerals refer to like parts throughout the description
of several views
of the drawings.
111
Date Recue/Date Received 2022-02-09
